Skydio R1

Two helmeted people bike in a scenic landscape while a black drone flies in front of them.
I've got my (13) eyes on you. Photo: Skydio

R1 is an autonomous camera drone that can track and follow a person or vehicle while capturing high-quality video and nimbly avoiding obstacles. It uses AI algorithms and 13 cameras for real-time navigation and subject tracking.

Creator

Skydio

Year
2018
Country
United States 🇺🇸
Categories
Features
Skydio R1: the self-flying camera. Video: Skydio

More videos

Rate this Robot

Overall Rating

Would you want this robot?

Appearance

Neutral

Did you know?

R1 uses simultaneous localization and mapping (SLAM) to construct and update a map of an environment, and keep track of a person's location within it.

Two views of a black drone with two rectangular side by side sections housing four rotors total, as well as having many cameras.
Top and side views. Photo: Skydio

History

Skydio was founded by Adam Bry, Abraham Bachrach, and Matt Donahoe, who met as grad students at MIT in 2009 where they worked on autonomous drone technology. After MIT they helped start Google's Project Wing, and in 2014 they founded Skydio, headquartered in San Mateo, Calif. In 2018 the company launched the Skydio R1, an autonomous drone for consumers and a platform for commercial development. The system that Skydio uses for autonomous navigation is entirely vision-based. There are 12 navigation cameras spaced all around the drone, including cameras that look down and up, and managing this massive inpouring of visual data is 256 cores worth of Nvidia TX1 GPU. Using machine learning, the Skydio drones are able to detect and avoid obstacles, and tracks a specific person and follow them while it does. In 2019, the company introduced its second-generation drone, Skydio 2, with a host of new autonomy features.

An illustration of the drone highlighting the locations of its many cameras.
R1 uses multiple cameras and AI to fly autonomously. Photo: Skydio

Specs

Overview

4K video capture. Hands-free operation with autonomous flight, tracking of people or vehicles, and dense obstacle avoidance.

Status

Ongoing

Year

2018

Website
Width
40 cm
Height
3.8 cm
Length
33 cm
Weight
1 kg
Speed
40 km/h
Sensors

12 navigation cameras for omnidirectional vision. One user video camera. Four inertial measurement units. GPS and barometer.

Actuators

4 motors

Materials

Carbon fiber (rotor guards), aluminum (fuselage)

Compute

NVIDIA Jetson TX1 with quad-core ARM CPUs, 4 GB RAM, and 256 CUDA cores (1 teraflops of performance)

Power

Rechargeable lithium-polymer batteries, 16 minutes of flight time

Cost
$2,499